Simona Vatrano

Zebra bodies recognition by artificial intelligence: A computational tool for Fabry nephropathy

Giorgio Cazzaniga, Maurizio Carbone, Gabriele Casati, Simona Vatrano et autres

Zebra bodies recognition by artificial intelligence (ZEBRA): a computational tool for Fabry nephropathy

Giorgio Cazzaniga, Maurizio Carbone, Raffaella Barretta, Gabriele Casati et autres

Fabry disease (FD) is a rare lysosomal storage disorder caused by mutations in the GLA gene, resulting in globotriaosylceramide accumulation. Kidney involvement (Fabry nephropathy) significantly contributes to morbidity and mortality. Diagnosis can be difficult, especially in females or late-onset variants. Renal biopsy …

it (code pays fourni par la source)

83P A fully-automated integrative workflow to support clinical decisions in molecular tumour boards

Mauro Giovanni Carta, M. Angeloni, Lars Tögel, Christoph D. Schubart et autres

In Molecular Tumour Boards (MTBs), next-generation sequencing (NGS)-based tumour molecular profiling is the basis to inform actionable alterations. Different bioinformatics tools and knowledge bases to support variant annotation, oncogenicity classification, as well as the estimation of complex biomarkers exist. However, continuous human …

de, it (code pays fourni par la source)

Liquid biopsy in prostate cancer: A multidisciplinary expert consensus statement

Francesco Pepe, Davide Seminati, Gustavo Baldassarre, Gabriella Cirmena et autres

Introduction BRCA1/2 testing via liquid biopsy has emerged as a critical, minimally invasive alternative to tissue sampling in metastatic castration-resistant prostate cancer (mCRPC), especially in the context of insufficient, inadequate, or unavailable tumor material. Methods A multidisciplinary panel of 18 Italian experts …

it (code pays fourni par la source)

Automatic labels are as effective as manual labels in digital pathology images classification with deep learning

Niccolò Marini, Stefano Marchesin, Lluis Borràs Ferrís, Simon Püttmann et autres

The increasing availability of biomedical data is helping to design more robust deep learning (DL) algorithms to analyze biomedical samples. Currently, one of the main limitations to training DL algorithms to perform a specific task is the need for medical experts to …

ch, it, de, pl, nl, bg, us (code pays fourni par la source)

Attention-Based Whole-Slide Image Compression Achieves Pathologist-Level Prescreening of Multiorgan Routine Histopathology Biopsies

Witali Aswolinskiy, Rachel S. van der Post, Michela Campora, Carla Baronchelli et autres

Screening programs for the early detection of cancers, such as colorectal and cervical cancers, have led to an increased demand for histopathological analysis of biopsies. Advanced image analysis with deep learning has shown the potential to automate cancer detection in digital pathology …

nl, it, se (code pays fourni par la source)

BRCA mutations and prostate cancer: should urologist improve daily clinical practice?

Simona Vatrano, Pietro Pepe, Ludovica Pepe, Cristina Alario et autres

INTRODUCTION: To evaluate BRCA1-2 (breast cancer) detection in men with high risk PCa, including the oncological consequences for the patient and family members. MATERIALS AND METHODS: From January 2023 to December 2024, 52 men (median age 73 years;) with confirmed PCa diagnosis …

it (code pays fourni par la source)

Attention-based whole-slide image compression achieves pathologist-level pre-screening of multi-organ routine histopathology biopsies

Witali Aswolinskiy, Rachel S. van der Post, Michiel Simons, Enrico Munari et autres

Abstract Screening programs for early detection of cancer such as colorectal and cervical cancer have led to an increased demand for histopathological analysis of biopsies. Advanced image analysis with Deep Learning has shown the potential to automate cancer detection in digital pathology …

nl, it, se (code pays fourni par la source)

Multimodal representations of biomedical knowledge from limited training whole slide images and reports using deep learning

Niccolò Marini, Stefano Marchesin, Marek Wodziński, Alessandro Caputo et autres

The increasing availability of biomedical data creates valuable resources for developing new deep learning algorithms to support experts, especially in domains where collecting large volumes of annotated data is not trivial. Biomedical data include several modalities containing complementary information, such as medical …

ch, it, pl, nl, bg (code pays fourni par la source)

Automatic Labels are as Effective as Manual Labels in Biomedical Images Classification with Deep Learning

Niccolò Marini, Stefano Marchesin, Lluis Borràs Ferrís, Simon Püttmann et autres

The increasing availability of biomedical data is helping to design more robust deep learning (DL) algorithms to analyze biomedical samples. Currently, one of the main limitations to train DL algorithms to perform a specific task is the need for medical experts to …

Benchmarking Hierarchical Image Pyramid Transformer for the Classification of Colon Biopsies and Polyps Histopathology Images

Nohemi Sofia Leon Contreras, Clément Grisi, Witali Aswolinskiy, Simona Vatrano et autres

Training neural networks with high-quality pixel-level annotation in histopathology whole-slide images (WSI) is an expensive process due to gigapixel resolution of WSIs. However, recent advances in self-supervised learning have shown that highly descriptive image representations can be learned without the need for …

nl (code pays fourni par la source)

Benchmarking Hierarchical Image Pyramid Transformer for the classification of colon biopsies and polyps in histopathology images

Nohemi Sofia Leon Contreras, Marina D’Amato, Francesco Ciompi, Clément Grisi et autres

Training neural networks with high-quality pixel-level annotation in histopathology whole-slide images (WSI) is an expensive process due to gigapixel resolution of WSIs. However, recent advances in self-supervised learning have shown that highly descriptive image representations can be learned without the need for …